Has anyone run a test of including some shibboleth or canary phrase or assertion in a chat, enabled for training, and seeing if it turns up later as something a model "knows"? I'd be curious to understand how that works even in a toy-level model, and if there is anyone consciously testing that process with the frontier lab offerings.
My naive instincts would be that it seems unlikely that a single chat transcript would leave much of an impression on a model, but I'd be very curious to learn how that works.
My naive instincts would be that it seems unlikely that a single chat transcript would leave much of an impression on a model, but I'd be very curious to learn how that works.